Federated Learning (FL) provides training of global shared model using decentralized data sources on edge nodes while preserving data privacy. However, it’s performance in the computer vision applications using Convolution neural network (CNN) considerably behind that of centralized training due to limited communication resources and low processing capability at edge nodes. Alternatively, Pure Vision transformer models (VIT) outperform CNNs by almost four times when it comes to computational efficiency and accuracy. Hence, we propose a new FL model with reconstructive strategy called FED-REV, Illustrates how attention-based structures (pure Vision Transformers) enhance FL accuracy over large and diverse data distributed over edge nodes, in addition to the proposed reconstruction strategy that determines the dimensions influence of each stage of the vision transformer and then reduce its dimension complexity which reduce computation cost of edge devices in addition to preserving accuracy achieved due to using the pure Vision transformer

Federated Learning, Vision Transformer, Model reconstruction.